Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1212 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.1274. Min Range: -7.1274
Max Act: 7.1274. Min Act: -0.1700
Data Index: 5574397 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1274. Min Range: -7.1274
Max Act: 7.1274. Min Act: -0.1700
Data Index: 2736625 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.9399. Min Act: -0.1700
Data Index: 8601982 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.8774. Min Act: -0.1700
Data Index: 1289533 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.8149. Min Act: -0.1700
Data Index: 7555231 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.8149. Min Act: -0.1700
Data Index: 5411953 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.7837. Min Act: -0.1700
Data Index: 7425148 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.7837. Min Act: -0.1700
Data Index: 7535449 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.8149. Min Act: -0.1700
Data Index: 5461487 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.7524. Min Act: -0.1700
Data Index: 3730838 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.7837. Min Act: -0.1700
Data Index: 2736617 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.7524. Min Act: -0.1700
Data Index: 2783858 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.7212. Min Act: -0.1700
Data Index: 3563953 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.7212. Min Act: -0.1700
Data Index: 3068159 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.7524. Min Act: -0.1700
Data Index: 7216872 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.7524. Min Act: -0.1700
Data Index: 8681684 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.7524. Min Act: -0.1700
Data Index: 1359228 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.6587. Min Act: -0.1700
Data Index: 4678289 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.6899. Min Act: -0.1700
Data Index: 8624557 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.6899. Min Act: -0.1700
Data Index: 8615563 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #19